AI Skill Hub 推荐使用:MCPMate 是一款优质的MCP工具。AI 综合评分 7.5 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
MCPMate 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
MCPMate 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/loocor/mcpmate
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcpmate": {
"command": "npx",
"args": ["-y", "mcpmate"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 MCPMate 执行以下任务... Claude: [自动调用 MCPMate MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"mcpmate": {
"command": "npx",
"args": ["-y", "mcpmate"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
English | 中文
<p align="center"> <img src="./assets/dashboard.png" alt="MCPMate dashboard" width="100%"> </p>
<p align="center"> <strong>Your progressive MCP management partner.</strong> </p>
<p align="center"> <a href="https://github.com/loocor/MCPMate/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-AGPL--3.0-blue" alt="License"></a> <img src="https://img.shields.io/badge/platform-macOS%20%7C%20Windows%20%7C%20Linux-lightgrey" alt="Platform"> <img src="https://img.shields.io/badge/Rust-1.75%2B-orange" alt="Rust"> <img src="https://img.shields.io/badge/Node.js-18%2B-brightgreen" alt="Node.js"> <a href="https://modelcontextprotocol.io/specification/2025-11-25"><img src="https://img.shields.io/badge/MCP-2025--11--25-purple" alt="MCP Spec"></a> </p>
---
Import MCP once. Start simple, then add profiles, per-client tools, and setup modes as your workflow grows. MCPMate is a local-first assistant that grows with you—not just another config file editor.
MCPMate sits between your AI apps and MCP servers so you manage connections once and send the right tools to each app. It works with Claude Desktop, Cursor, Codex, Zed, VS Code, CLI tools, and other clients that follow the standard MCP config format.
Easy to begin, built to scale: one import with low friction; the same setup still fits as MCP spreads across more clients, servers, and scenarios—no product swap, no restart ritual.
| Stage | What you get |
|---|---|
| **Start** | Import servers, verify calls, and see health in one place |
| **Grow** | Scene profiles for coding, writing, or research; switch the full tool set in one click |
| **Tune** | Per-client trimming from one shared server library—less clutter, lower token use |
| **Choose how to connect** | **Transparent** (native config output), **Hosted** (durable proxy control), or **Unify** (small tool surface, on-demand discovery) |
Live site: mcp.umate.ai · Docs: mcp.umate.ai/docs
| Feature | Description |
|---|---|
| **Profile-Based Trimming** | Organize MCP servers into scene, app, and dynamic profiles. Switch instantly without restarting services. |
| **Multi-Client Support** | Detect, configure, and manage Claude Desktop, Cursor, Zed, Codex, and user-defined clients. |
| **Dynamic Client Governance** | Database-first governance with Allow/Deny policies. No static template files. Verified config targets required for writes. |
| **Market Integration** | Browse and install from the official MCP registry without leaving the app. OAuth-capable servers supported with callback authorization. |
| **Runtime Manager** | Installs and manages Node.js, uv (Python), and Bun runtimes used by local MCP servers. |
| **OAuth 2.0 Upstream (PKCE)** | Supports upstream OAuth 2.0 flows with PKCE for Streamable HTTP MCP servers, including metadata discovery and callback handling. |
| **Built-in redb Cache** | L2 embedded cache for capability snapshots and frequently accessed proxy state. |
| **Structured Logs** | Dedicated Logs page with cursor-based pagination, actor/target/action metadata, and REST API access. |
| **Browser Extension** | Chrome/Edge extension detects mcpServers snippets on web pages and imports them via mcpmate://import/server. |
| **Tool Inspector** | Run quick tool calls against connected servers and inspect structured responses from the console. |
Prerequisites: Rust 1.75+, Node.js 18+ or Bun, SQLite 3
1. Clone & Build the Backend
git clone https://github.com/loocor/MCPMate.git
cd MCPMate/backend
cargo build --release
2. Start the Proxy
cargo run --release
The proxy starts with: - REST API on http://localhost:8080 - MCP endpoint on http://localhost:8000
3. Launch the Dashboard
cd ../board
bun install
bun run dev
Dashboard available at http://localhost:5173.
Download the latest release for your platform from GitHub Releases.
Note: macOS builds are signed and notarized to reduce system security prompts and improve package trust.
Coming soon. An online environment will let you explore the dashboard, profiles, and client configuration without a local setup.
高质量的MCP管理工具
该工具使用 AGPL-3.0 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。
总体来看,MCPMate 是一款质量良好的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | mcpmate |
| 原始描述 | 开源MCP工具:MCPMate is a progressive MCP management center for organizing servers, clients, 。⭐25 · Rust |
| Topics | mcpmcp-clientmcp-servermcpmaterust |
| GitHub | https://github.com/loocor/mcpmate |
| License | AGPL-3.0 |
| 语言 | Rust |
收录时间:2026-06-05 · 更新时间:2026-06-08 · License:AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端